# SurgXBench: Explainable Vision-Language Model Benchmark for Surgery

arXiv: https://arxiv.org/abs/2505.10764 · HTML: https://mlsanity.com/paper/2505.10764/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos](https://mlsanity.com/paper/2109.03223/) (2021)
- [Evaluating Weakly Supervised Object Localization Methods Right](https://mlsanity.com/paper/2001.07437/) (2020)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures](https://mlsanity.com/paper/2307.15220/) (2023)
- [HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition](https://mlsanity.com/paper/2405.10075/) (2024)
- [Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation](https://mlsanity.com/paper/2410.00263/) (2024)
- [From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks](https://mlsanity.com/paper/2406.06579/) (2024)
- [LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning](https://mlsanity.com/paper/2408.07981/) (2024)
- [ToolNet: Holistically-Nested Real-Time Segmentation of Robotic Surgical Tools](https://mlsanity.com/paper/1706.08126/) (2017)
- [Causal Interpretation of Self-Attention in Pre-Trained Transformers](https://mlsanity.com/paper/2310.20307/) (2023)
- [LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models](https://mlsanity.com/paper/2404.03118/) (2024)
- [Attention-Guided Lightweight Network for Real-Time Segmentation of Robotic Surgical Instruments](https://mlsanity.com/paper/1910.11109/) (2019)
- [Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models](https://mlsanity.com/paper/2410.09750/) (2024)
- [LC-GAN: Image-to-image Translation Based on Generative Adversarial Network for Endoscopic Images](https://mlsanity.com/paper/2003.04949/) (2020)
- [Multi-frame Feature Aggregation for Real-time Instrument Segmentation in Endoscopic Video](https://mlsanity.com/paper/2011.08752/) (2020)

## Built on by (most cited first, 6 of 6)

- [SurgSigma: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence](https://mlsanity.com/paper/2603.16822/) (2026)
- [TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models](https://mlsanity.com/paper/2603.06999/) (2026)
- [A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling](https://mlsanity.com/paper/2603.27341/) (2026)
- [Evaluating and Understanding Model Editing for Medical Vision Language Models](https://mlsanity.com/paper/2607.05310/) (2026)
- [Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition](https://mlsanity.com/paper/2607.19889/) (2026)
- [Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI](https://mlsanity.com/paper/2608.05258/) (2026)

## Abstract (arXiv)

Innovations in digital intelligence are transforming robotic surgery with more informed decision-making. Real-time awareness of surgical instrument presence and actions (e.g., cutting tissue) is essential for such systems. Yet, despite decades of research, most machine learning models for this task are trained on small datasets and still struggle to generalize. Recently, vision-Language Models (VLMs) have brought transformative advances in reasoning across visual and textual modalities. Their unprecedented generalization capabilities suggest great potential for advancing intelligent robotic surgery. However, surgical VLMs remain under-explored, and existing models show limited performance, highlighting the need for benchmark studies to assess their capabilities and limitations and to inform future development. To this end, we benchmark the zero-shot performance of several advanced VLMs on two public robotic-assisted laparoscopic datasets for instrument and action classification. Beyond standard evaluation, we integrate explainable AI to visualize VLM attention and uncover causal explanations behind their predictions. This provides a previously underexplored perspective in this field for evaluating the reliability of model predictions. We also propose several explainability analysis-based metrics to complement standard evaluations. Our analysis reveals that surgical VLMs, despite domain-specific training, often rely on weak contextual cues rather than clinically relevant visual evidence, highlighting the need for stronger visual and reasoning supervision in surgical applications.